© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7480
    Prev
    Next
    INDEX
    Explanations

    a seemingly random set of capital letters and number combinations

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms or phrases

    np_token-act-pair-logits · gpt-4o-mini

    genetic/code sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.59
    webElementGuid
    -0.57
    ButterKnife
    -0.56
     invokingState
    -0.56
    URLException
    -0.55
    HtmlAttribute
    -0.54
    ModelAttribute
    -0.52
    deepcopy
    -0.52
    lait
    -0.52
     referrerpolicy
    -0.50
    POSITIVE LOGITS
    culares
    0.50
     تانيه
    0.49
     Révolution
    0.47
     himo
    0.46
    odb
    0.45
    Counters
    0.45
    chants
    0.44
    सन्दर्भ
    0.44
     réuss
    0.44
    μον
    0.43
    Activations Density 1.186%

    No Known Activations